Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal actions and interpersonal interactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rather
    -0.74
    ortment
    -0.69
    itton
    -0.67
    yrinth
    -0.63
    ciplinary
    -0.61
    unknown
    -0.61
    okingly
    -0.61
    not
    -0.61
    accompanied
    -0.60
    Discussion
    -0.60
    POSITIVE LOGITS
     anymore
    2.03
     nor
    1.57
     anything
    1.39
     any
    1.32
     anybody
    1.26
     whatsoever
    1.26
     slightest
    1.23
     anywhere
    1.17
     ANY
    1.16
     anyone
    1.12
    Act Density 1.974%

    No Known Activations